Build a full game (code, art, audio) with AI
Exact prompt
Game jam, scaled down: in one pass build a complete small arcade game as a single file index.html (no external assets or libraries). Theme: "a capybara crossing a river". Must include: a title screen with Start, keyboard controls, procedurally drawn art on a <canvas> (no image files), at least 2 sound effects and background music generated with the Web Audio API (start audio on user gesture), a score, increasing difficulty, a game-over screen with restart, and a high score saved in localStorage.
Task prompt given to the agent (headless, offline, synthetic fixture inputs): Game jam, scaled down: in one pass build a complete small arcade game as a single file index.html (no external assets or libraries). Theme: "a capybara crossing a river". Must include: a title screen with Start, keyboard controls, procedurally drawn art on a <canvas> (no image files), at least 2 sound effects and background music generated with the Web Audio API (start audio on user gesture), a score, increasing difficulty, a game-over screen with restart, and a high score saved in localStorage. Inspired by https://x.com/qusaxz/status/2077427986689843623 (unverified; not checked with the author). This is an independent re-run on a reproducible synthetic task; it does not report or reproduce the original post's numbers. Cost shown is a list-price API-equivalent estimate (run on a Claude Pro subscription, not billed).
Success criteria: All automated rubric checks pass: single file, no external libs/assets; canvas drawing; Web Audio; oscillator music/sfx; title/start screen; game over + restart; localStorage high score; capybara theme; no uncaught console errors.
Best model for this task so far: Gemma 4 31B Instruct (Venice) (success, $0.0049, 3m). Best AI model for Games & Simulations →
All runs (8)
88% pass rate across 8 eligible runs: 7 pass, 0 partial, 1 fail. Partial and failed runs are listed below with everything else.ⓘ
| Model | Cost | Time | Step-insⓘ | Autonomy | Outcome | Trustⓘ | Date | Compare |
|---|---|---|---|---|---|---|---|---|
| AClaude Haiku 5.5default · thinking on | $0.05 | 10m | 0 | Fully autonomous | pass | Trust 80% | 2026-10-16 | |
| DDeepSeek V4.1 Flash (Venice)thinking off | $0.04 | 2m | 0 | Fully autonomous | pass | Trust 80% | 2026-10-16 | |
| XGrok 4.3 (Venice) | $0.01 | 25s | 0 | Fully autonomous | pass | Trust 80% | 2026-10-15 | |
| QQwen3 Coder 480B Turbo (Venice) | $0.0061 | 29s | 0 | Fully autonomous | pass | Trust 80% | 2026-10-15 | |
| DDeepSeek V4.1 Flash (Venice) | $0.02 | 1m | 0 | Fully autonomous | fail | Trust 80% | 2026-10-14 | |
| GGemma 4 31B Instruct (Venice) | $0.0049 | 3m | 0 | Fully autonomous | pass | Trust 80% | 2026-10-14 | |
| AClaude Opus 5.5 | $1.00 | 5m | 0 | Fully autonomous | pass | Trust 80% | 2026-10-14 | |
| AClaude Sonnet 5.5 | $0.19 | 1m | 0 | Fully autonomous | pass | Trust 80% | 2026-10-14 |
Embed this result
A live badge for this use case. It links back here and updates as new runs are published.
Get new runs and ranking changes weekly
Which models got better or cheaper on real tasks like this one.